Image super-resolution using registration of wavelet multi-scale components with affine transformation

Yasutaka Matsuo, Ryoki Takada, Shinya Iwasaki, Jiro Katto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 Citations (Scopus)

    Abstract

    We propose a novel image super-resolution method from digital cinema to 8K ultra high-definition television using registration of wavelet multi-scale components with affine transformation. The proposed method features that an original image is divided into signal and noise components by the wavelet soft-shrinkage with detection of white noise level. The signal component enhances resolution by registration between a signal component and its wavelet multi-scale components with affine transformation and parameters optimization. The affine transformation enhances super-resolution image quality because it increases registration candidates. The noise component enhances resolution with power control considering cinema noise representation. Super-resolution image outputs by synthesis of super-resolved signal and noise components. Experiments show that the proposed method has objectively better PSNR measurement and subjectively better appearance in comparison with conventional super-resolution methods.

    Original languageEnglish
    Title of host publicationProceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013
    Pages279-282
    Number of pages4
    DOIs
    Publication statusPublished - 2013
    Event15th IEEE International Symposium on Multimedia, ISM 2013 - Anaheim, CA
    Duration: 2013 Dec 92013 Dec 11

    Other

    Other15th IEEE International Symposium on Multimedia, ISM 2013
    CityAnaheim, CA
    Period13/12/913/12/11

    Fingerprint

    High definition television
    White noise
    Image resolution
    Power control
    Image quality
    Experiments

    Keywords

    • Affine transformation
    • Digital cinema
    • Image super-resolution
    • Registration
    • Ultra high-definition television

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Human-Computer Interaction
    • Software

    Cite this

    Matsuo, Y., Takada, R., Iwasaki, S., & Katto, J. (2013). Image super-resolution using registration of wavelet multi-scale components with affine transformation. In Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013 (pp. 279-282). [6746805] https://doi.org/10.1109/ISM.2013.53

    Image super-resolution using registration of wavelet multi-scale components with affine transformation. / Matsuo, Yasutaka; Takada, Ryoki; Iwasaki, Shinya; Katto, Jiro.

    Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. p. 279-282 6746805.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Matsuo, Y, Takada, R, Iwasaki, S & Katto, J 2013, Image super-resolution using registration of wavelet multi-scale components with affine transformation. in Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013., 6746805, pp. 279-282, 15th IEEE International Symposium on Multimedia, ISM 2013, Anaheim, CA, 13/12/9. https://doi.org/10.1109/ISM.2013.53
    Matsuo Y, Takada R, Iwasaki S, Katto J. Image super-resolution using registration of wavelet multi-scale components with affine transformation. In Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. p. 279-282. 6746805 https://doi.org/10.1109/ISM.2013.53
    Matsuo, Yasutaka ; Takada, Ryoki ; Iwasaki, Shinya ; Katto, Jiro. / Image super-resolution using registration of wavelet multi-scale components with affine transformation. Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. pp. 279-282
    @inproceedings{a9e19fc4b1204bb4b80be21aaca7938d,
    title = "Image super-resolution using registration of wavelet multi-scale components with affine transformation",
    abstract = "We propose a novel image super-resolution method from digital cinema to 8K ultra high-definition television using registration of wavelet multi-scale components with affine transformation. The proposed method features that an original image is divided into signal and noise components by the wavelet soft-shrinkage with detection of white noise level. The signal component enhances resolution by registration between a signal component and its wavelet multi-scale components with affine transformation and parameters optimization. The affine transformation enhances super-resolution image quality because it increases registration candidates. The noise component enhances resolution with power control considering cinema noise representation. Super-resolution image outputs by synthesis of super-resolved signal and noise components. Experiments show that the proposed method has objectively better PSNR measurement and subjectively better appearance in comparison with conventional super-resolution methods.",
    keywords = "Affine transformation, Digital cinema, Image super-resolution, Registration, Ultra high-definition television",
    author = "Yasutaka Matsuo and Ryoki Takada and Shinya Iwasaki and Jiro Katto",
    year = "2013",
    doi = "10.1109/ISM.2013.53",
    language = "English",
    isbn = "9780769551401",
    pages = "279--282",
    booktitle = "Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013",

    }

    TY - GEN

    T1 - Image super-resolution using registration of wavelet multi-scale components with affine transformation

    AU - Matsuo, Yasutaka

    AU - Takada, Ryoki

    AU - Iwasaki, Shinya

    AU - Katto, Jiro

    PY - 2013

    Y1 - 2013

    N2 - We propose a novel image super-resolution method from digital cinema to 8K ultra high-definition television using registration of wavelet multi-scale components with affine transformation. The proposed method features that an original image is divided into signal and noise components by the wavelet soft-shrinkage with detection of white noise level. The signal component enhances resolution by registration between a signal component and its wavelet multi-scale components with affine transformation and parameters optimization. The affine transformation enhances super-resolution image quality because it increases registration candidates. The noise component enhances resolution with power control considering cinema noise representation. Super-resolution image outputs by synthesis of super-resolved signal and noise components. Experiments show that the proposed method has objectively better PSNR measurement and subjectively better appearance in comparison with conventional super-resolution methods.

    AB - We propose a novel image super-resolution method from digital cinema to 8K ultra high-definition television using registration of wavelet multi-scale components with affine transformation. The proposed method features that an original image is divided into signal and noise components by the wavelet soft-shrinkage with detection of white noise level. The signal component enhances resolution by registration between a signal component and its wavelet multi-scale components with affine transformation and parameters optimization. The affine transformation enhances super-resolution image quality because it increases registration candidates. The noise component enhances resolution with power control considering cinema noise representation. Super-resolution image outputs by synthesis of super-resolved signal and noise components. Experiments show that the proposed method has objectively better PSNR measurement and subjectively better appearance in comparison with conventional super-resolution methods.

    KW - Affine transformation

    KW - Digital cinema

    KW - Image super-resolution

    KW - Registration

    KW - Ultra high-definition television

    UR - http://www.scopus.com/inward/record.url?scp=84900658444&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84900658444&partnerID=8YFLogxK

    U2 - 10.1109/ISM.2013.53

    DO - 10.1109/ISM.2013.53

    M3 - Conference contribution

    SN - 9780769551401

    SP - 279

    EP - 282

    BT - Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013

    ER -